Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 567 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 5.1187. Min Range: -5.1187
Max Act: 5.1187. Min Act: -0.1700
Data Index: 1126377 (C4 (Web Text))
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1187. Min Range: -5.1187
Max Act: 5.0874. Min Act: -0.1700
Data Index: 53659 (C4 (Web Text))
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1187. Min Range: -5.1187
Max Act: 5.0249. Min Act: -0.1700
Data Index: 228291 (C4 (Web Text))
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1187. Min Range: -5.1187
Max Act: 4.8687. Min Act: -0.1700
Data Index: 23717 (C4 (Web Text))
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1187. Min Range: -5.1187
Max Act: 4.8687. Min Act: -0.1700
Data Index: 1134141 (C4 (Web Text))
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1187. Min Range: -5.1187
Max Act: 4.8999. Min Act: -0.1700
Data Index: 334355 (C4 (Web Text))
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1187. Min Range: -5.1187
Max Act: 4.9312. Min Act: -0.1700
Data Index: 1167276 (C4 (Web Text))
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1187. Min Range: -5.1187
Max Act: 4.8687. Min Act: -0.1700
Data Index: 442038 (C4 (Web Text))
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1187. Min Range: -5.1187
Max Act: 4.8687. Min Act: -0.1700
Data Index: 1228043 (C4 (Web Text))
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1187. Min Range: -5.1187
Max Act: 4.8374. Min Act: -0.1700
Data Index: 218383 (C4 (Web Text))
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1187. Min Range: -5.1187
Max Act: 4.8374. Min Act: -0.1700
Data Index: 552978 (C4 (Web Text))
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1187. Min Range: -5.1187
Max Act: 4.8374. Min Act: -0.1700
Data Index: 1035478 (C4 (Web Text))
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1187. Min Range: -5.1187
Max Act: 4.8062. Min Act: -0.1700
Data Index: 652067 (C4 (Web Text))
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1187. Min Range: -5.1187
Max Act: 4.7749. Min Act: -0.1700
Data Index: 982007 (C4 (Web Text))
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1187. Min Range: -5.1187
Max Act: 4.7749. Min Act: -0.1700
Data Index: 670440 (C4 (Web Text))
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1187. Min Range: -5.1187
Max Act: 4.6812. Min Act: -0.1700
Data Index: 999966 (C4 (Web Text))
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1187. Min Range: -5.1187
Max Act: 4.6499. Min Act: -0.1700
Data Index: 1285948 (C4 (Web Text))
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1187. Min Range: -5.1187
Max Act: 4.6186. Min Act: -0.1700
Data Index: 330416 (C4 (Web Text))
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1187. Min Range: -5.1187
Max Act: 4.5874. Min Act: -0.1700
Data Index: 378524 (C4 (Web Text))
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1187. Min Range: -5.1187
Max Act: 4.6499. Min Act: -0.1700
Data Index: 711131 (C4 (Web Text))
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #19